Fast dynamic 1D simulation of divertor plasmas with neural PDE surrogates

Y Poels, G Derks, E Westerhof, K Minartz… - Nuclear …, 2023 - iopscience.iop.org
Managing divertor plasmas is crucial for operating reactor scale tokamak devices due to
heat and particle flux constraints on the divertor target. Simulation is an important tool to …

Machine learning for advancing low-temperature plasma modeling and simulation

J Trieschmann, L Vialetto… - Journal of Micro …, 2023 - spiedigitallibrary.org
Machine learning has had an enormous impact in many scientific disciplines. It has also
attracted significant interest in the field of low-temperature plasma (LTP) modeling and …

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning

N Zolman, U Fasel, JN Kutz, SL Brunton - arXiv preprint arXiv:2403.09110, 2024 - arxiv.org
Deep reinforcement learning (DRL) has shown significant promise for uncovering
sophisticated control policies that interact in environments with complicated dynamics, such …

Bifurcation-like transition of divertor conditions induced by X-point radiation in KSTAR L-mode plasmas

JS Park, R Pitts, J Jang, YS Han, W Choe, J Lore… - Nuclear …, 2023 - iopscience.iop.org
Density ramps with ion grad B drift directed into lower single null KSTAR L-mode plasmas
are associated with a simultaneous and abrupt reduction of the divertor particle flux on both …

Gpsindy: Data-driven discovery of equations of motion

J Hsin, S Agarwal, A Thorpe… - arXiv preprint arXiv …, 2023 - arxiv.org
In this paper, we consider the problem of discovering dynamical system models from noisy
data. The presence of noise is known to be a significant problem for symbolic regression …

Data-driven optimal control of undulatory swimming

K Maroun, P Traoré, M Bergmann - Physics of Fluids, 2024 - pubs.aip.org
Achieving precise control over self-propelled undulatory swimmers requires a deep
understanding of their intricate dynamics. This paper presents a method for addressing …

Evaluation of SPARC divertor conditions in H-mode operation using SOLPS-ITER

JD Lore, JS Park, T Eich, AQ Kuang, ML Reinke… - Nuclear …, 2024 - iopscience.iop.org
The predicted divertor conditions for the SPARC tokamak are calculated using SOLPS-ITER
for a range of scrape-off-layer (SOL) heat flux widths \lamq, input powers, and particle …

Shallow Recurrent Decoder for Reduced Order Modeling of Plasma Dynamics

JN Kutz, M Reza, F Faraji, A Knoll - arXiv preprint arXiv:2405.11955, 2024 - arxiv.org
Reduced order models are becoming increasingly important for rendering complex and
multiscale spatio-temporal dynamics computationally tractable. The computational efficiency …

High-Fidelity Data-Driven Dynamics Model for Reinforcement Learning-based Magnetic Control in HL-3 Tokamak

N Wu, Z Yang, R Li, N Wei, Y Chen, Q Dong… - arXiv preprint arXiv …, 2024 - arxiv.org
The drive to control tokamaks, a prominent technology in nuclear fusion, is essential due to
its potential to provide a virtually unlimited source of clean energy. Reinforcement learning …

[HTML][HTML] Sparse regression for plasma physics

AA Kaptanoglu, C Hansen, JD Lore, M Landreman… - Physics of …, 2023 - pubs.aip.org
Many scientific problems can be formulated as sparse regression, ie, regression onto a set
of parameters when there is a desire or expectation that some of the parameters are exactly …